DiegoCaraballo/Email-extractor
1
1
Fork 0
mirror of https://github.com/DiegoCaraballo/Email-extractor.git synced 2024-09-20 06:46:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix .decode('utf-8')

Browse source
This commit is contained in:
Diego Caraballo 2022-07-21 14:55:03 -03:00
parent ca70b86aa9
commit dc65b03bf1
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
EmailExtractor.py
View file

@ -688,7 +688,7 @@ def extractOnlyUrl(url):
if(status != 200 or contentType == "audio/mpeg"):
raise ValueError('Bad Url...')
html = conn.read().decode('utf-8')
html = conn.read().decode(conn.headers.get_content_charset())
emails = re.findall(r'[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}', html)
@ -743,7 +743,7 @@ def extractUrl(url):
if(status != 200 or contentType == "audio/mpeg"):
raise ValueError('Bad Url...')
html = conn.read().decode('utf-8')
html = conn.read().decode(conn.headers.get_content_charset())
emails = re.findall(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}", html)
print ("Searching in " + url)